WFUMB Ultrasound Open最新文献

英文中文

Added clinical advantage of combining ultrasound with radiograph in assessing ankle injuries: Comparison with MRI

WFUMB Ultrasound Open

Pub Date : 2025-02-19 DOI: 10.1016/j.wfumbo.2025.100081

Yanni He , Wenhong Yi , Chenqian Guo , Wenjun Li , Changpeng Xu , Jialin Ye , Sushu Li , Meijun Zhou , Tong Bai , Tong Wang , Lixian Liu , Ning Zhang , Yu Wang , Jingjiao Xu , Hongmei Liu

Objectives

To compare the diagnostic accuracy of ultrasound (US) and magnetic resonance imaging (MRI) for ankle ligament injuries, and evaluate ankle injury using the combination of US and X-ray.

Materials and methods

A retrospective study was conducted on 1419 participants presenting with ankle injury at hospital between July 2020 and March 2022. 1153 patients included after exclusion underwent US imaging, while 584 patients were also diagnosed by X-ray and 78 accepted MRI. The diagnostic abilities of MRI and US for ankle ligamentous injuries (anterior inferior tibiofibular ligament (AITFL), anterior talofibular ligament (ATFL), calcaneofibular ligament (CFL), medial deltoid ligament (MDL)) were compared by Wilcoxon signed-rank test. The diagnostic performance of US for ligamentous tear was evaluated in terms of sensitivity, specificity, and AUC value, with MRI as the reference standard. The detection rates of X-ray imaging, US imaging, and their combination were compared by Kendall's W test and Wilcoxon signed-rank test.

Results

The study population included 558 males and 595 females with a mean age of 30 ± 13 years. There were no significant differences on the grade of ligament injury detected by US and MRI (P _AITFL = 0.52, P _ATFL = 0.15, P _CAL = 0.061, P _MDL = 0.26). The diagnostic sensitivity, specificity and AUC of US imaging for ligamentous tear were 50.0 %, 88.9 % and 0.69 in AITFL, 92.7 %, 60.9 % and 0.77 in ATFL, 90.9 %, 86.6 % and 0.89 in CFL, 66.7 %, 96.0 % and 0.81 in MDL respectively. The detection rate of bone fracture increased significantly after combining US and X-ray imaging (R _{US & x-ray} = 42.6 %, R _US = 36.5 %, R _x-ray = 26.5 %, P < 0.0001).

Conclusion

US imaging showed similar diagnostic performance for AITFL, ATFL, CFL and MDL injury as MRI. The combination of US and X-ray imaging can be a useful complementary tool for primary evaluation of ankle injuries.

{"title":"Added clinical advantage of combining ultrasound with radiograph in assessing ankle injuries: Comparison with MRI","authors":"Yanni He , Wenhong Yi , Chenqian Guo , Wenjun Li , Changpeng Xu , Jialin Ye , Sushu Li , Meijun Zhou , Tong Bai , Tong Wang , Lixian Liu , Ning Zhang , Yu Wang , Jingjiao Xu , Hongmei Liu","doi":"10.1016/j.wfumbo.2025.100081","DOIUrl":"10.1016/j.wfumbo.2025.100081","url":null,"abstract":"<div><h3>Objectives</h3><div>To compare the diagnostic accuracy of ultrasound (US) and magnetic resonance imaging (MRI) for ankle ligament injuries, and evaluate ankle injury using the combination of US and X-ray.</div></div><div><h3>Materials and methods</h3><div>A retrospective study was conducted on 1419 participants presenting with ankle injury at hospital between July 2020 and March 2022. 1153 patients included after exclusion underwent US imaging, while 584 patients were also diagnosed by X-ray and 78 accepted MRI. The diagnostic abilities of MRI and US for ankle ligamentous injuries (anterior inferior tibiofibular ligament (AITFL), anterior talofibular ligament (ATFL), calcaneofibular ligament (CFL), medial deltoid ligament (MDL)) were compared by Wilcoxon signed-rank test. The diagnostic performance of US for ligamentous tear was evaluated in terms of sensitivity, specificity, and AUC value, with MRI as the reference standard. The detection rates of X-ray imaging, US imaging, and their combination were compared by Kendall's W test and Wilcoxon signed-rank test.</div></div><div><h3>Results</h3><div>The study population included 558 males and 595 females with a mean age of 30 ± 13 years. There were no significant differences on the grade of ligament injury detected by US and MRI (P <sub>AITFL</sub> = 0.52, P <sub>ATFL</sub> = 0.15, P <sub>CAL</sub> = 0.061, P <sub>MDL</sub> = 0.26). The diagnostic sensitivity, specificity and AUC of US imaging for ligamentous tear were 50.0 %, 88.9 % and 0.69 in AITFL, 92.7 %, 60.9 % and 0.77 in ATFL, 90.9 %, 86.6 % and 0.89 in CFL, 66.7 %, 96.0 % and 0.81 in MDL respectively. The detection rate of bone fracture increased significantly after combining US and X-ray imaging (R <sub>US & x-ray</sub> = 42.6 %, R <sub>US</sub> = 36.5 %, R <sub>x-ray</sub> = 26.5 %, P < 0.0001).</div></div><div><h3>Conclusion</h3><div>US imaging showed similar diagnostic performance for AITFL, ATFL, CFL and MDL injury as MRI. The combination of US and X-ray imaging can be a useful complementary tool for primary evaluation of ankle injuries.</div></div>","PeriodicalId":101281,"journal":{"name":"WFUMB Ultrasound Open","volume":"3 1","pages":"Article 100081"},"PeriodicalIF":0.0,"publicationDate":"2025-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143508517","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Treatment of inoperable pancreatic adenocarcinoma with focused ultrasound and microbubbles in patients receiving chemotherapy

WFUMB Ultrasound Open

Pub Date : 2025-01-31 DOI: 10.1016/j.wfumbo.2025.100080

Margrete Haram , Rune Hansen , Ola Finneng Myhre , Stian Solberg , Naseh Amini , Bjørn Atle Angelsen , Catharina de Lange Davies , Eva Hofsli

Objective

Preclinical trials have demonstrated promising results for increased tumor uptake and therapeutic effect of drugs combined with focused ultrasound (FUS) and microbubbles (MBs). The aim of this clinical trial was to investigate whether FUS and MB could improve the effect of chemotherapy in patients with inoperable pancreatic ductal adenocarcinoma (PDAC) and to investigate safety and feasibility.

Methods

Twenty patients with inoperable PDAC were included and randomized for either chemotherapy combined with FUS and MBs or only chemotherapy, but one patient in the FUS and MB group had later to be excluded. A new dual-frequency transducer for imaging (4.5 MHz) and treatment (0.35 MHz) was used. After chemotherapy (FOLFIRINOX or nab-paclitaxel-gemcitabine), the treatment group was exposed to FUS (frequency 0.35 MHz, mechanical index 0.5, pulse length 2.9 ms (1000 cycles), pressure amplitude 0.3 MPa and MBs (SonoVue) for 35 min). Nine boluses of MBs were injected intravenously (i.v) with a 3.5 min interval. Patients were scheduled for two months of treatment. Changes in the size of tumors were determined from Computed Tomography (CT) -images.

Results

Treatment with FUS and MB is safe with the used settings. No additional effects of FUS and MBs regarding tumor volume or resectability were observed. Overall survival increased, from 9.8 months to 11.7 months for the patients receiving FUS + MB, although not statistically significant.

Conclusion

FUS combined with MBs is a safe, feasible, and available strategy for potentially improving the effect of chemotherapy in pancreatic cancer patients. Therapeutic effect was not demonstrated in this trial. Reducing the time between chemotherapy and injection of MB and FUS and optimization of ultrasound parameters may improve the treatment effect. Multicenter trials with standardized protocols should be performed.

{"title":"Treatment of inoperable pancreatic adenocarcinoma with focused ultrasound and microbubbles in patients receiving chemotherapy","authors":"Margrete Haram , Rune Hansen , Ola Finneng Myhre , Stian Solberg , Naseh Amini , Bjørn Atle Angelsen , Catharina de Lange Davies , Eva Hofsli","doi":"10.1016/j.wfumbo.2025.100080","DOIUrl":"10.1016/j.wfumbo.2025.100080","url":null,"abstract":"<div><h3>Objective</h3><div>Preclinical trials have demonstrated promising results for increased tumor uptake and therapeutic effect of drugs combined with focused ultrasound (FUS) and microbubbles (MBs). The aim of this clinical trial was to investigate whether FUS and MB could improve the effect of chemotherapy in patients with inoperable pancreatic ductal adenocarcinoma (PDAC) and to investigate safety and feasibility.</div></div><div><h3>Methods</h3><div>Twenty patients with inoperable PDAC were included and randomized for either chemotherapy combined with FUS and MBs or only chemotherapy, but one patient in the FUS and MB group had later to be excluded. A new dual-frequency transducer for imaging (4.5 MHz) and treatment (0.35 MHz) was used. After chemotherapy (FOLFIRINOX or nab-paclitaxel-gemcitabine), the treatment group was exposed to FUS (frequency 0.35 MHz, mechanical index 0.5, pulse length 2.9 ms (1000 cycles), pressure amplitude 0.3 MPa and MBs (SonoVue) for 35 min). Nine boluses of MBs were injected intravenously (i.v) with a 3.5 min interval. Patients were scheduled for two months of treatment. Changes in the size of tumors were determined from Computed Tomography (CT) -images.</div></div><div><h3>Results</h3><div>Treatment with FUS and MB is safe with the used settings. No additional effects of FUS and MBs regarding tumor volume or resectability were observed. Overall survival increased, from 9.8 months to 11.7 months for the patients receiving FUS + MB, although not statistically significant.</div></div><div><h3>Conclusion</h3><div>FUS combined with MBs is a safe, feasible, and available strategy for potentially improving the effect of chemotherapy in pancreatic cancer patients. Therapeutic effect was not demonstrated in this trial. Reducing the time between chemotherapy and injection of MB and FUS and optimization of ultrasound parameters may improve the treatment effect. Multicenter trials with standardized protocols should be performed.</div></div>","PeriodicalId":101281,"journal":{"name":"WFUMB Ultrasound Open","volume":"3 1","pages":"Article 100080"},"PeriodicalIF":0.0,"publicationDate":"2025-01-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143354802","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Breast cancer ultrasound image segmentation using improved 3DUnet++

WFUMB Ultrasound Open

Pub Date : 2025-01-21 DOI: 10.1016/j.wfumbo.2024.100068

Saba Hesaraki , Abdul Sajid Mohammed , Mehrshad Eisaei , Ramin Mousa

Breast cancer is the most common cancer and the main cause of cancer-related deaths in women around the world. Early detection reduces the number of deaths. Automated breast ultrasound (ABUS) is a new and promising screening method for examining the entire breast. Volumetric ABUS examination is time-consuming, and lesions may be missed during the examination. Therefore, computer-aided cancer diagnosis in ABUS volume is highly expected to help the physician for breast cancer screening. In this research, we presented 3D structures based on UNet, ResUNet, and UNet++ for the automatic detection of cancer in ABUS volume to speed up examination while providing high detection sensitivity with low false positives (FPs). The three investigated approaches were evaluated on equal datasets in terms of training and testing as well as with proportional hyperparameters. Among the proposed approaches in classification and segmentation problems, the UNet++ approach was able to achieve more acceptable results. The UNet++ approach on the dataset of the Tumor Segmentation, Classification, and Detection Challenge on Automated 3D Breast Ultrasound 2023 (Named TSCD-ABUS2023) was able to achieve Accuracy = 0.9911 and AUROC = 0.9761 in classification and Dice = 0.4930 in segmentation.

{"title":"Breast cancer ultrasound image segmentation using improved 3DUnet++","authors":"Saba Hesaraki , Abdul Sajid Mohammed , Mehrshad Eisaei , Ramin Mousa","doi":"10.1016/j.wfumbo.2024.100068","DOIUrl":"10.1016/j.wfumbo.2024.100068","url":null,"abstract":"<div><div>Breast cancer is the most common cancer and the main cause of cancer-related deaths in women around the world. Early detection reduces the number of deaths. Automated breast ultrasound (ABUS) is a new and promising screening method for examining the entire breast. Volumetric ABUS examination is time-consuming, and lesions may be missed during the examination. Therefore, computer-aided cancer diagnosis in ABUS volume is highly expected to help the physician for breast cancer screening. In this research, we presented 3D structures based on UNet, ResUNet, and UNet++ for the automatic detection of cancer in ABUS volume to speed up examination while providing high detection sensitivity with low false positives (FPs). The three investigated approaches were evaluated on equal datasets in terms of training and testing as well as with proportional hyperparameters. Among the proposed approaches in classification and segmentation problems, the UNet++ approach was able to achieve more acceptable results. The UNet++ approach on the dataset of the Tumor Segmentation, Classification, and Detection Challenge on Automated 3D Breast Ultrasound 2023 (Named TSCD-ABUS2023) was able to achieve Accuracy = 0.9911 and AUROC = 0.9761 in classification and Dice = 0.4930 in segmentation.</div></div>","PeriodicalId":101281,"journal":{"name":"WFUMB Ultrasound Open","volume":"3 1","pages":"Article 100068"},"PeriodicalIF":0.0,"publicationDate":"2025-01-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143376510","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Utilization of evoked vibrational signatures under ultrasound examination as a novel method of tissue classification

WFUMB Ultrasound Open

Pub Date : 2025-01-08 DOI: 10.1016/j.wfumbo.2024.100078

Baxton R. Chen

Background

Ultrasound interpretation requires extensive training and can be subjective and inexact. We previously reported a novel method of identifying tissues by analyzing the evoked vibrational signatures based on inherent tissue structural integrity and density during ultrasound examination. We now demonstrate the evoked tissue vibrational signatures of different tissues.

Results

During ultrasound examination, the evoked vibrational signatures are detected by a portable dynamic signal recorder and interpreted based on time, amplitude, dampening, and frequency on single or multiple degrees of freedom. Various organs and tissue types were examined using ultrasound and unique vibrational signatures were recorded and stored in a proprietary database. Representative signatures of liver, kidney, lungs, and muscles were demonstrated, and their vibration frequencies and amplitudes were compared.

Conclusion

We developed a method of using vibrational signatures to identify tissues under ultrasound examination, and we now report the signatures of different tissue types.

{"title":"Utilization of evoked vibrational signatures under ultrasound examination as a novel method of tissue classification","authors":"Baxton R. Chen","doi":"10.1016/j.wfumbo.2024.100078","DOIUrl":"10.1016/j.wfumbo.2024.100078","url":null,"abstract":"<div><h3>Background</h3><div>Ultrasound interpretation requires extensive training and can be subjective and inexact. We previously reported a novel method of identifying tissues by analyzing the evoked vibrational signatures based on inherent tissue structural integrity and density during ultrasound examination. We now demonstrate the evoked tissue vibrational signatures of different tissues.</div></div><div><h3>Results</h3><div>During ultrasound examination, the evoked vibrational signatures are detected by a portable dynamic signal recorder and interpreted based on time, amplitude, dampening, and frequency on single or multiple degrees of freedom. Various organs and tissue types were examined using ultrasound and unique vibrational signatures were recorded and stored in a proprietary database. Representative signatures of liver, kidney, lungs, and muscles were demonstrated, and their vibration frequencies and amplitudes were compared.</div></div><div><h3>Conclusion</h3><div>We developed a method of using vibrational signatures to identify tissues under ultrasound examination, and we now report the signatures of different tissue types.</div></div>","PeriodicalId":101281,"journal":{"name":"WFUMB Ultrasound Open","volume":"3 1","pages":"Article 100078"},"PeriodicalIF":0.0,"publicationDate":"2025-01-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143160096","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Protocol refinement and inter- and intra-rater reliability assessment of ultrasound-based measurements of hamstring architecture, and echo intensity, and intra-rater reliability of shear wave elastography

WFUMB Ultrasound Open

Pub Date : 2025-01-07 DOI: 10.1016/j.wfumbo.2025.100079

Maria Belinda Cristina C. Fidel , Jan Tyrone Cabrera , Christine Grace V. Ogerio , Johann Querijero , Helen A. Banwell , Consuelo B. Gonzalez-Suarez

Objectives

The increase in hamstring injuries highlights gaps in current understanding and prevention strategies. Hamstring architecture, quality, and mechanical properties influence force production, offering key insights into muscle health and function. This study aims to refine a standardized protocol for hamstring image acquisition and digitization and to assess inter- and intra-rater reliability of measurements like fascicle length, pennation angle, muscle thickness, cross-sectional area, echo intensity, and shear wave elastography.

Methods

This study had two phases: pilot and protocol refinement and intra- and inter-rater reliability of image digitization of fascicle length, pennation angle, muscle thickness, cross-sectional area, and echo intensity and intra-rater reliability of shear wave elastography using intra-class correlation coefficient.

Results

This study developed and refined a hamstring image acquisition and digitization protocol, focusing on architecture, quality, and stiffness along its length at rest and during isometric contraction. Using Image J, intra-rater reliability for digitizing fascicle length, pennation angle, muscle thickness, cross-sectional area, and echo intensity was excellent. Inter-rater reliability ranged from moderate to excellent across all variables. Shear wave elastography showed moderate to excellent intra-rater reliability, with higher consistency during contraction than rest.

Conclusion

The authors refined a standardized protocol for ultrasound imaging of hamstring architecture, quality, and stiffness, as well as digitization of fascicle length, pennation angle, muscle thickness, cross-sectional area, and echo intensity at rest and during isometric contraction using ImageJ. The protocol demonstrated moderate to excellent intra- and inter-rater reliability, with image markings further enhancing measurement consistency.

{"title":"Protocol refinement and inter- and intra-rater reliability assessment of ultrasound-based measurements of hamstring architecture, and echo intensity, and intra-rater reliability of shear wave elastography","authors":"Maria Belinda Cristina C. Fidel , Jan Tyrone Cabrera , Christine Grace V. Ogerio , Johann Querijero , Helen A. Banwell , Consuelo B. Gonzalez-Suarez","doi":"10.1016/j.wfumbo.2025.100079","DOIUrl":"10.1016/j.wfumbo.2025.100079","url":null,"abstract":"<div><h3>Objectives</h3><div>The increase in hamstring injuries highlights gaps in current understanding and prevention strategies. Hamstring architecture, quality, and mechanical properties influence force production, offering key insights into muscle health and function. This study aims to refine a standardized protocol for hamstring image acquisition and digitization and to assess inter- and intra-rater reliability of measurements like fascicle length, pennation angle, muscle thickness, cross-sectional area, echo intensity, and shear wave elastography.</div></div><div><h3>Methods</h3><div>This study had two phases: pilot and protocol refinement and intra- and inter-rater reliability of image digitization of fascicle length, pennation angle, muscle thickness, cross-sectional area, and echo intensity and intra-rater reliability of shear wave elastography using intra-class correlation coefficient.</div></div><div><h3>Results</h3><div>This study developed and refined a hamstring image acquisition and digitization protocol, focusing on architecture, quality, and stiffness along its length at rest and during isometric contraction. Using Image J, intra-rater reliability for digitizing fascicle length, pennation angle, muscle thickness, cross-sectional area, and echo intensity was excellent. Inter-rater reliability ranged from moderate to excellent across all variables. Shear wave elastography showed moderate to excellent intra-rater reliability, with higher consistency during contraction than rest.</div></div><div><h3>Conclusion</h3><div>The authors refined a standardized protocol for ultrasound imaging of hamstring architecture, quality, and stiffness, as well as digitization of fascicle length, pennation angle, muscle thickness, cross-sectional area, and echo intensity at rest and during isometric contraction using ImageJ. The protocol demonstrated moderate to excellent intra- and inter-rater reliability, with image markings further enhancing measurement consistency.</div></div>","PeriodicalId":101281,"journal":{"name":"WFUMB Ultrasound Open","volume":"3 1","pages":"Article 100079"},"PeriodicalIF":0.0,"publicationDate":"2025-01-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143160097","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A proposal to use bubble exposure time instead of bubble count to grade PFOs

WFUMB Ultrasound Open

Pub Date : 2024-12-24 DOI: 10.1016/j.wfumbo.2024.100077

Ruud W. Keunen, Mark M. Rubin, Emily Ho

引用次数: 0

Erratum regarding missing disclaimer in previously published articles

WFUMB Ultrasound Open

Pub Date : 2024-12-01 DOI: 10.1016/j.wfumbo.2024.100072

Saubhagya Srivastava, Garvit D. Khatri

引用次数: 0

Cutoff value of ultrasonic attenuation coefficient by Att.PLUS technique for diagnosis and grading of hepatic steatosis using MRI-derived proton density fat fraction (MRI-PDFF) as a reference standard

WFUMB Ultrasound Open

Pub Date : 2024-12-01 DOI: 10.1016/j.wfumbo.2024.100043

Natthaporn Tanpowpong , Aimpavee Keeratiratwattana , Pisit Tangkijvanich

引用次数: 0

Corrigendum to “Ultrasound imaging measurements to determine reduced diaphragm thickness and relevance to breathing pattern disorders diagnosis in females” [WFUMB Ultrasound Open 1 (2) (2023) 100010]

WFUMB Ultrasound Open

Pub Date : 2024-12-01 DOI: 10.1016/j.wfumbo.2024.100071

S. Peirce , S. Mooney , M. Rohan , R. Ellis

引用次数: 0

Detection of fetal congenital heart defects on three-vessel view ultrasound videos 通过三血管视图超声视频检测胎儿先天性心脏缺陷

WFUMB Ultrasound Open

Pub Date : 2024-11-23 DOI: 10.1016/j.wfumbo.2024.100075

Netzahualcoyotl Hernandez-Cruz , Olga Patey , Bojana Salovic , Divyanshu Mishra , Md Mostafa Kamal Sarker , Aris Papageorghiou , J. Alison Noble

Background:

Detecting congenital heart defects (CHDs) is challenging due to the difficulty of identifying subtle abnormalities in fetal heart structures.

Objectives:

To develop a deep learning-based method for segmenting vessels in the three-vessel view (3VV) to characterise the vessels by size and spatial relationships to detect abnormal fetal hearts.

Methods:

We present a deep learning-based method that takes as input a fetal heart ultrasound (US) video of the three vessels view (3VV) and an anchor frame, which contains the segmentation of the pulmonary artery (PA), aorta (Ao), and superior vena cava (SVC) in the 3VV. The method automatically segments the anatomical structures subsequent to the anchor frame and classifies the US video as normal or abnormal. The method consists of two phases. The first phase combines three residual networks (ResNets) extended with a self-attention block and a refinement module. The second phase extends a ResNet with two CoordConv layers integrating spatial coordinates. We assess segmentation performance using the intersection over union (IoU) and dice similarity coefficient (DSC) metrics and classification of US videos using sensitivity and specificity. We also investigate the tolerance to failure of the method by introducing mislabelled anchor frames. The dataset used in this study consists of 150 US videos of the 3VV; 50 videos were used for training, and 100 videos (50 normal videos, 50 abnormal videos) for testing.

Results:

In terms of anatomical structure segmentation accuracy, the method achieves an average IoU of 89.5% (99.5% for PA, 85.0% for Ao, and 84.1% for SVC), and an average DSC of 0.950% (0.946% for PA, 0.969% for Ao, and 0.934% for SVC). Detection of abnormal videos achieved a sensitivity of 0.99 and specificity of 1.0. The tolerance to failure analysis shows a decrease in the sensitivity of 0.023 and 0.015 for normal and abnormal case videos, respectively.

Conclusions:

The initial evaluation of our approach to fetal CHDs on 3VV ultrasound videos is promising but requires further refinement and evaluation on a larger dataset to assess clinical utility. The approach is designed to be translatable to low-resource settings where fetal echocardiography experts are unavailable due to the simple acquisition protocol.

背景：由于难以识别胎儿心脏结构的细微异常，检测先天性心脏缺陷（CHD）具有挑战性。目的：开发一种基于深度学习的方法，用于分割三血管视图（3VV）中的血管，通过血管的大小和空间关系来描述血管的特征，从而检测异常胎心。方法：我们提出了一种基于深度学习的方法，该方法将三血管视图（3VV）的胎儿心脏超声（US）视频和锚帧作为输入，锚帧包含三血管视图中肺动脉（PA）、主动脉（Ao）和上腔静脉（SVC）的分割。该方法可自动分割锚定帧后的解剖结构，并将 US 视频分为正常或异常。该方法包括两个阶段。第一阶段将三个残差网络（ResNets）与一个自注意模块和一个细化模块相结合。第二阶段通过两个整合空间坐标的 CoordConv 层对 ResNet 进行扩展。我们使用 "交集大于联合"（IoU）和 "骰子相似系数"（DSC）指标评估分割性能，并使用灵敏度和特异性评估美国视频的分类。我们还通过引入错误标记的锚帧（anchor frames）研究了该方法对失败的容忍度。本研究使用的数据集由 150 个 3VV US 视频组成；其中 50 个视频用于训练，100 个视频（50 个正常视频和 50 个异常视频）用于测试。结果：在解剖结构分割准确性方面，该方法的平均 IoU 为 89.5%（PA 为 99.5%，Ao 为 85.0%，SVC 为 84.1%），平均 DSC 为 0.950%（PA 为 0.946%，Ao 为 0.969%，SVC 为 0.934%）。异常视频检测的灵敏度为 0.99，特异性为 1.0。结论：我们对 3VV 超声波视频中胎儿心脏缺损的初步评估结果很有希望，但还需要进一步完善，并在更大的数据集上进行评估，以评估临床实用性。由于采集方案简单，该方法可应用于缺乏胎儿超声心动图专家的低资源环境。

{"title":"Detection of fetal congenital heart defects on three-vessel view ultrasound videos","authors":"Netzahualcoyotl Hernandez-Cruz , Olga Patey , Bojana Salovic , Divyanshu Mishra , Md Mostafa Kamal Sarker , Aris Papageorghiou , J. Alison Noble","doi":"10.1016/j.wfumbo.2024.100075","DOIUrl":"10.1016/j.wfumbo.2024.100075","url":null,"abstract":"<div><h3>Background:</h3><div>Detecting congenital heart defects (CHDs) is challenging due to the difficulty of identifying subtle abnormalities in fetal heart structures.</div></div><div><h3>Objectives:</h3><div>To develop a deep learning-based method for segmenting vessels in the three-vessel view (3VV) to characterise the vessels by size and spatial relationships to detect abnormal fetal hearts.</div></div><div><h3>Methods:</h3><div>We present a deep learning-based method that takes as input a fetal heart ultrasound (US) video of the three vessels view (3VV) and an anchor frame, which contains the segmentation of the pulmonary artery (PA), aorta (Ao), and superior vena cava (SVC) in the 3VV. The method automatically segments the anatomical structures subsequent to the anchor frame and classifies the US video as normal or abnormal. The method consists of two phases. The first phase combines three residual networks (ResNets) extended with a self-attention block and a refinement module. The second phase extends a ResNet with two CoordConv layers integrating spatial coordinates. We assess segmentation performance using the intersection over union (IoU) and dice similarity coefficient (DSC) metrics and classification of US videos using sensitivity and specificity. We also investigate the tolerance to failure of the method by introducing mislabelled anchor frames. The dataset used in this study consists of 150 US videos of the 3VV; 50 videos were used for training, and 100 videos (50 normal videos, 50 abnormal videos) for testing.</div></div><div><h3>Results:</h3><div>In terms of anatomical structure segmentation accuracy, the method achieves an average IoU of 89.5% (99.5% for PA, 85.0% for Ao, and 84.1% for SVC), and an average DSC of 0.950% (0.946% for PA, 0.969% for Ao, and 0.934% for SVC). Detection of abnormal videos achieved a sensitivity of 0.99 and specificity of 1.0. The tolerance to failure analysis shows a decrease in the sensitivity of 0.023 and 0.015 for normal and abnormal case videos, respectively.</div></div><div><h3>Conclusions:</h3><div>The initial evaluation of our approach to fetal CHDs on 3VV ultrasound videos is promising but requires further refinement and evaluation on a larger dataset to assess clinical utility. The approach is designed to be translatable to low-resource settings where fetal echocardiography experts are unavailable due to the simple acquisition protocol.</div></div>","PeriodicalId":101281,"journal":{"name":"WFUMB Ultrasound Open","volume":"2 2","pages":"Article 100075"},"PeriodicalIF":0.0,"publicationDate":"2024-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142720135","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

下一页尾页

类型

全部化学•材料生命科学医学物理工程技术环境•农林材料科学地球科学法学管理学化学环境科学与生态学计算机科学教育学经济学农林科学人文科学生物学数学物理与天体物理心理学综合性期刊其他工业工程理学历史学农学文学信息工程

数据库

全部 ACS Publications Elsevier ieeexplore Springer The Royal Society of Chemistry Wiley

期刊

WFUMB Ultrasound Open

全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.

﹀